CtrlK
BlogDocsLog inGet started
Tessl Logo

fusion-issue-solving

Handles GitHub issue resolution end-to-end for prompts like "solve #123", "lets solve #123", "work on #123", "work on https://github.com/owner/repo/issues/123", or by pasting a direct GitHub issue URL as the request. USE FOR: solve #123, continue work on issue #123, work on https://github.com/owner/repo/issues/123, paste a GitHub issue URL for implementation work. DO NOT USE FOR: issue drafting only, PR review only, or non-implementation research.

66

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, clearly sequenced workflow with strong validation checkpoints and good progressive disclosure. It loses points on conciseness (trigger duplication, verbose assignee logic) and actionability (a mix of concrete specifics and abstract procedural direction with no executable examples).

Suggestions

Remove the duplicate trigger list in the "When to use" section since the same phrasings already appear in the frontmatter description, or trim it to a one-line pointer.

Collapse the repeated primary-issue vs. sub-issue assignee bullets in step 3 into a single rule applied per issue.

Tighten abstract steps like "Build and track a concrete plan" and "Implement in small scoped changes" with a concrete expectation (e.g., specific todo granularity or change-size hint) to raise actionability.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes Claude's competence, but the "When to use" trigger list duplicates the frontmatter description and the assignee-checking sub-bullets (step 3) repeat near-identical logic for primary vs. sub-issues, so it could be tightened.

2 / 3

Actionability

Concrete specifics are present (PR body path `.tmp/pr-body-issue-123-scope-summary.md`, ~20 read / ~5 mutation budgets, GraphQL 5-point cost, PR template), but several steps are abstract procedural direction ("Build and track a concrete plan", "Implement in small scoped changes") with no executable examples, fitting "some concrete guidance but incomplete".

2 / 3

Workflow Clarity

Ten numbered steps give a clear sequence with an explicit validate→fix→re-run feedback loop (step 8) and confirmation checkpoints before mutations (step 10), supported by a checklist asset.

3 / 3

Progressive Disclosure

The body is a well-sectioned overview (When to use, Required inputs, Instructions, Expected output, Assets, Safety) with a single clearly-signaled, verified one-level-deep reference to assets/issue-solving-checklist.md.

3 / 3

Total

10

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit trigger guidance and clear use/non-use boundaries that minimize conflict risk. The only weakness is that it states the capability broadly rather than enumerating concrete constituent actions.

DimensionReasoningScore

Specificity

The description names the domain and a broad action ("Handles GitHub issue resolution end-to-end") but does not enumerate multiple concrete sub-actions (e.g., research, implement, prepare PR) within the description itself, so it is not a comprehensive action list.

2 / 3

Completeness

It explicitly states what the skill does ("Handles GitHub issue resolution end-to-end") and provides explicit when-guidance via "USE FOR:" and "DO NOT USE FOR:" clauses, satisfying both required parts.

3 / 3

Trigger Term Quality

It covers natural phrasings a user would actually say — "solve #123", "lets solve #123", "work on #123", direct issue URLs, and "continue work on issue #123" — giving strong coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The niche is clear (end-to-end implementation issue resolution) and the explicit "DO NOT USE FOR: issue drafting only, PR review only, or non-implementation research" boundary distinguishes it from sibling authoring/review skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
equinor/fusion-framework
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.